Extraction of Binary Black Hole Gravitational Wave Signals from Detector Data Using Deep Learning. (arXiv:2105.03073v3 [gr-qc] UPDATED)
<a href="http://arxiv.org/find/gr-qc/1/au:+Chatterjee_C/0/1/0/all/0/1">Chayan Chatterjee</a>, <a href="http://arxiv.org/find/gr-qc/1/au:+Wen_L/0/1/0/all/0/1">Linqing Wen</a>, <a href="http://arxiv.org/find/gr-qc/1/au:+Diakogiannis_F/0/1/0/all/0/1">Foivos Diakogiannis</a>, <a href="http://arxiv.org/find/gr-qc/1/au:+Vinsen_K/0/1/0/all/0/1">Kevin Vinsen</a>
Accurate extractions of the detected gravitational wave (GW) signal waveforms
are essential to validate a detection and to probe the astrophysics behind the
sources producing the GWs. This however could be difficult in realistic
scenarios where the signals detected by existing GW detectors could be
contaminated with non-stationary and non-Gaussian noise. While the performance
of existing waveform extraction methods are optimal, they are not fast enough
for online application, which is important for multi-messenger astronomy. In
this paper, we demonstrate that a deep learning architecture consisting of
Convolutional Neural Network and bidirectional Long Short-Term Memory
components can be used to extract binary black hole (BBH) GW waveforms from
realistic noise in a few milli-seconds. We have tested our network
systematically on injected GW signals, with component masses uniformly
distributed in the range of 10 to 80 solar masses, on Gaussian noise and LIGO
detector noise. We find that our model can extract GW waveforms with overlaps
of more than 0.95 with pure Numerical Relativity templates for signals with
signal-to-noise ratio (SNR) greater than six, and is also robust against
interfering glitches. We then apply our model to all ten detected BBH events
from the first (O1) and second (O2) observation runs, obtaining greater than
0.97 overlaps for all ten extracted BBH waveforms with the corresponding pure
templates. We discuss the implication of our result and its future applications
to GW localization and mass estimation.
Accurate extractions of the detected gravitational wave (GW) signal waveforms
are essential to validate a detection and to probe the astrophysics behind the
sources producing the GWs. This however could be difficult in realistic
scenarios where the signals detected by existing GW detectors could be
contaminated with non-stationary and non-Gaussian noise. While the performance
of existing waveform extraction methods are optimal, they are not fast enough
for online application, which is important for multi-messenger astronomy. In
this paper, we demonstrate that a deep learning architecture consisting of
Convolutional Neural Network and bidirectional Long Short-Term Memory
components can be used to extract binary black hole (BBH) GW waveforms from
realistic noise in a few milli-seconds. We have tested our network
systematically on injected GW signals, with component masses uniformly
distributed in the range of 10 to 80 solar masses, on Gaussian noise and LIGO
detector noise. We find that our model can extract GW waveforms with overlaps
of more than 0.95 with pure Numerical Relativity templates for signals with
signal-to-noise ratio (SNR) greater than six, and is also robust against
interfering glitches. We then apply our model to all ten detected BBH events
from the first (O1) and second (O2) observation runs, obtaining greater than
0.97 overlaps for all ten extracted BBH waveforms with the corresponding pure
templates. We discuss the implication of our result and its future applications
to GW localization and mass estimation.
http://arxiv.org/icons/sfx.gif
